Buckets:

rtrm's picture
download
raw
6.05 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;BERTología&quot;,&quot;local&quot;:&quot;bertología&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
<link href="/docs/transformers/main/es/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/entry/start.b4301699.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/chunks/scheduler.36a0863c.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/chunks/singletons.a6ab9d4a.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/chunks/index.733708bb.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/chunks/paths.815a7736.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/entry/app.eaf9d9af.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/chunks/index.f891bdb2.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/nodes/0.e9e5a018.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/chunks/each.e59479a4.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/nodes/6.d1cb8b2f.js">
<link rel="modulepreload" href="/docs/transformers/main/es/_app/immutable/chunks/EditOnGithub.a58e27a9.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;BERTología&quot;,&quot;local&quot;:&quot;bertología&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="bertología" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#bertología"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>BERTología</span></h1> <p data-svelte-h="svelte-t8qs96">Hay un creciente campo de estudio empeñado en la investigación del funcionamiento interno de los transformers de gran escala como BERT
(que algunos llaman “BERTología”). Algunos buenos ejemplos de este campo son:</p> <ul data-svelte-h="svelte-1sb7ig0"><li>BERT Rediscovers the Classical NLP Pipeline por Ian Tenney, Dipanjan Das, Ellie Pavlick:
<a href="https://arxiv.org/abs/1905.05950" rel="nofollow">https://arxiv.org/abs/1905.05950</a></li> <li>Are Sixteen Heads Really Better than One? por Paul Michel, Omer Levy, Graham Neubig: <a href="https://arxiv.org/abs/1905.10650" rel="nofollow">https://arxiv.org/abs/1905.10650</a></li> <li>What Does BERT Look At? An Analysis of BERT’s Attention por Kevin Clark, Urvashi Khandelwal, Omer Levy, Christopher D.
Manning: <a href="https://arxiv.org/abs/1906.04341" rel="nofollow">https://arxiv.org/abs/1906.04341</a></li> <li>CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure: <a href="https://arxiv.org/abs/2210.04633" rel="nofollow">https://arxiv.org/abs/2210.04633</a></li></ul> <p data-svelte-h="svelte-f71qwa">Para asistir al desarrollo de este nuevo campo, hemos incluido algunas features adicionales en los modelos BERT/GPT/GPT-2 para
ayudar a acceder a las representaciones internas, principalmente adaptado de la gran obra de Paul Michel
(<a href="https://arxiv.org/abs/1905.10650" rel="nofollow">https://arxiv.org/abs/1905.10650</a>):</p> <ul data-svelte-h="svelte-wp6xpp"><li>accediendo a todos los hidden-states de BERT/GPT/GPT-2,</li> <li>accediendo a todos los pesos de atención para cada head de BERT/GPT/GPT-2,</li> <li>adquiriendo los valores de salida y gradientes de las heads para poder computar la métrica de importancia de las heads y realizar la poda de heads como se explica
en <a href="https://arxiv.org/abs/1905.10650" rel="nofollow">https://arxiv.org/abs/1905.10650</a>.</li></ul> <p data-svelte-h="svelte-1wml3jh">Para ayudarte a entender y usar estas features, hemos añadido un script específico de ejemplo: <a href="https://github.com/huggingface/transformers/tree/main/examples/research_projects/bertology/run_bertology.py" rel="nofollow">bertology.py</a> mientras extraes información y cortas un modelo pre-entrenado en
GLUE.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/es/bertology.md" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
{
__sveltekit_8nzhgd = {
assets: "/docs/transformers/main/es",
base: "/docs/transformers/main/es",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/transformers/main/es/_app/immutable/entry/start.b4301699.js"),
import("/docs/transformers/main/es/_app/immutable/entry/app.eaf9d9af.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 6],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
6.05 kB
·
Xet hash:
13482e7ef1405ff4fdb82f8ae68a161fad97dd7f38eac39f1428617cce9f38c0

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.